Control of sevofluran rate with a neuro - fuzzy system in the inhalation anesthesia

CONTROL OF SEVOFLURAN RATE WITH A NEURO-FUZZY SYSTEM IN THE INHALATION ANESTHESIA SUMMARY Key words: Depth of anesthesia, Neuro-fuzzy Control, EEG power spectrum. It is a significant problem to determine and to control the anesthesia depth during general anesthesia in surgical applications. Since the depth of anesthesia can vary from one moment to another, current medical technics have not the ability of holding anesthesia depth in exact stability and in a reliable level. EEG has been recommended in numerous studies on the determination of the anesthesia depth as a significat method. In recent years the interest in the use of EEG about the determination of the anesthesia depth has increased. A relation between anesthesia dose and various EEG parameters (EEG power spectrum, bispectral index (BIS) etc.)has been stated in the latest studies. In this study, power spectrum of the EEG data and the heartbeat data obtained from 25 patients has been applied to the designed Neuro-Fuzzy system. The designed system has been composed of two parts; one is an artificial neural network and the other is a Fuzzy system. A backpropagation artificial neural network has been developed which contains 53 nodes in the input layer, 27 nodes in the hidden and 1 node in the output layer. In the artificial neural network inputs, the power spectral density values corresponding 1-50 Hz frequency interval of the EEG slices which has 10 seconds of time interval, the ratio of the total of the PSD values of current EEG slice to the total PSD values of EEG slice of pre-anaesthesia, the ratio of the total PSD values of the EEG data to the total PSD values of the previous EEG data, and the previous anaesthetic gas ratio values have been applied and the network has been educated. At the end of the education total error has been found as 10"17. In the fuzzy system block, the ratio of current heartbeat to the previous one, the ratio of the current heartbeat to the pre-operation heartbeat, the ratio of the output of the artificial neural network to the previous applied anaesthetic gas have been applied as variables and in the system output gas ratio prediction has been obtained as percentage. The designed Neuro-Fuzzy system has been tested by using 10 data set obtained from 4 different patients. In the anesthetic gas prediction according to the anesthesia level, successful results have been obtained with the designed system. xv